Tag: AI

  • Copilot Outside of SSMS Seems to Work

    I read Brent’s first look at SSMS and Copilot in there. He didn’t have a great opinion of the tool, especially comparing it to Gemini or Claude. I haven’t tested this yet, mostly because I’ve got other stuff going on, but I decided to take his prompt and the code and drop it into the dedicated Copilot App on my Windows 11 laptop.

    This is part of a series of experiments with AI systems.

    I have a button that starts Copilot, so I pressed it and put in this prompt:

    2025-05_line0075

    This was copied from Brent’s post, and then his code copied and dropped in.

    I was curious to see if this worked.

    My Results

    I thought my results were better. The first part of the response is shown below. Copilot sees the scalar function as a problem and rewrites things. I don’t love that this is just the query and not the CREATE OR ALTER PROC part, but still.

    2025-05_line0073

    Below this, it notes that I should test indexes and gives me the ones it would recommend. Then it goes into the fact that order by desc can be problematic. It also has a TOP 1 recommendation for the first query.

    2025-05_line0074

    The rest of the response is OK, and gets into some general things that might help me go past the recommendations.

    2025-05_line0076

    The prompting matters, as if I click on the “what are more perf opt techniques” I get a lot of generic stuff.

    2025-05_line0078

    Is AI going to make you a better DBA or developer? Maybe. It will give you things to think about, but you need to test them. You might even ask a GenAI tool for help on that. I did and got this:

    2025-05_line0079

    And below, some more steps.

    2025-05_line0080

    Not bad, and likely what a lot of people do, though perhaps not with #5, in which HammerDB is suggested to run this proc.

    Learn to use GenAI tools, learn where they help (And save time) and where they can’t be trusted. That’s likely an ongoing battle for most of us, but these tools can help us be more productive.

  • Changing the Paradigm of Work

    I saw an article on AI usage that is based on an upcoming book that suggests redesigning the world around new tech, not adding it to existing things. The first example is how electricity was introduced to existing factories, but it only provided some incremental gains until new factories were redesigned around electric motors. There’s also an example given about reworking hotels to remove the front desk since that feature isn’t needed. Instead, people could walk in, and an employee with a tablet could find them to check them in.

    I’m all for rethinking and redesigning processes. I do think we have a huge glut of software in many organizations that exists because processes have evolved across time, but not everything and we keep our old software. When we have a new need or want a new capability, we add new software (or add features), but we don’t necessarily throw out all the old software, processes, or habits. That wouldn’t be practical, often because when we implement something new, it might not meet all our needs. Or at least we don’t know it meets our needs at first.

    I don’t love the examples, especially as I see organizations where Teams/Slack are heavily in use (not just in tech companies), and these tools have changed how people work. Not everyone has moved, and there is a lot of document sharing and legacy systems, but that’s also because not everyone wants to or can change at the same pace. However, lots of people have changed how they create, share, collaborate, communicate, and more because of these tools.

    I also think the hotel example is silly (read the article to see more). I don’t need a desk, and often I check in and get my key without ever visiting a desk. However, I do like the desk because when I need something, I want to be able to find someone, not wander around looking for an employee or waiting for them to respond to some page. When there’s a desk I can see someone is there. I certainly don’t want a kiosk with an AI there to queue at to request a person help me.

    GenAI LLMs are going to change work for a lot of people, especially those in tech. I don’t know that we can redesign the way we work now, as the technology is still advancing, and I’m not sure how we will want to integrate agents with GenAI to do work. We have to experiment and find ways to use this tech before we build too much. We also have to see it mature.

    When we do, I bet many more people will start to use AI to generate code, change settings, deploy things, and more. I’m also sure that they will make many mistakes, at scale, and we’ll be using a GenAI agent to undo things, or perhaps we’ll have humans scrambling to fix systems. I wouldn’t be surprised to see the humans commonly fixing things as we might not trust the AI Agent (or our prompting) to fix our mistake.

    If you could redesign work, what would you want out of an AI? Assume that it is at least as competent as someone you work with. Is there a way that a GenAI system would make your work smoother?

    Steve Jones

    Listen to the podcast at Libsyn, Spotify, or iTunes.

    Note, podcasts are only available for a limited time online.

  • Using AI to Test a SQL Query

    Someone sent me this code.

    WITH p AS
     ( SELECT ID, ROW_NUMBER() OVER (ORDER BY ID ASC) AS RN
     FROM wp_posts
     WHERE post_parent = 94341; )
     UPDATE p SET menu_order = RN

    That’s not great code. In fact, it won’t run. I know that, but does an AI? Let’s see how Copilot does.

    This is part of a series of experiments with AI systems.

    The First Test

    I entered this prompt, but accidentally hit Enter. When I then pasted in the code and hit enter, I got this:

    2025-05_line0012

    That is just about what I would have sent the author to let them know this code doesn’t work. It’s good to see a GenAI LLM can recognize this.

    I then pasted in the entire prompt which was: “give me a table with the schema to match this code: WITH p AS ( SELECT ID, ROW_NUMBER() OVER (ORDER BY ID ASC) AS RN FROM wp_posts WHERE post_parent = 94341; ) UPDATE p SET menu_order = RN

    The Gen AI response was polite, with this answer:

    Certainly! Based on your SQL code, it looks like you need a table schema that matches the structure of wp_posts, particularly including ID, post_parent, and menu_order. Here’s a possible schema:

    I then had this code, with a copy button that I could copy/paste into SSMS.

    CREATE TABLE wp_posts (
         ID INT PRIMARY KEY,      -- Unique identifier for each post
         post_parent INT,         -- Parent post ID (for hierarchical structures)
         menu_order INT           -- Order value for arranging posts
    );

    That’s what I would have done to mock this up for testing. You might guess the next step: data.

    Here’s my prompt: create some test data for the table with Ids that increment but are not necessarily sequential and post_parent values that match the ID values

    That got my this response.

    2025-05_line0016

    That’s not bad, but it’s a limited set of data. Let’s ask for more.

    2025-05_line0031

    Below this the GenAI LLM gave me a summary that explains what it did.

    2025-05_line0032

    Next, I wanted a test. I used this prompt: write a tsqlt test to verify that the update statement works to reset the menu_order to sequential values for a particular post_parent

    I got a nice response and the code I’m showing below the image.

    2025-05_line0033

    Here is the code:

    -- Step 1: Create a test class
    EXEC tSQLt.NewTestClass 'TestMenuOrderUpdate';

    GO

     

    — Step 2: Define the test
    CREATE PROCEDURE TestMenuOrderUpdate.[test_UpdateMenuOrder_Sequential]
    AS
    BEGIN
    — Arrange: Fake the wp_posts table
    EXEC tSQLt.FakeTable ‘dbo.wp_posts’;

     

    INSERT INTO wp_posts (ID, post_parent, menu_order)
    VALUES
    (101, 94341, 5), (102, 94341, 3), (103, 94341, 8),
    (104, 94341, 1), (105, 94341, 7);

     

    — Act: Run the update logic
    WITH p AS (
    SELECT ID, ROW_NUMBER() OVER (ORDER BY ID ASC) AS RN
    FROM wp_posts
    WHERE post_parent = 94341
    )
    UPDATE wp_posts
    SET menu_order = p.RN
    FROM p
    WHERE wp_posts.ID = p.ID;

     

    — Assert: Check if menu_order is sequential
    EXEC tSQLt.AssertEqualsTable ‘ExpectedResults’, ‘wp_posts’;

     

    END;
    GO

     

    — Step 3: Create expected results table for assertion
    CREATE TABLE ExpectedResults (
    ID INT PRIMARY KEY,
    post_parent INT,
    menu_order INT
    );

     

    INSERT INTO ExpectedResults (ID, post_parent, menu_order)
    VALUES
    (101, 94341, 1), (102, 94341, 2), (103, 94341, 3),
    (104, 94341, 4), (105, 94341, 5);

     

    — Run the test
    EXEC tSQLt.Run ‘TestMenuOrderUpdate’;

    
    

    This is where I stopped. This code runs, though it’s brittle in that the Expected Results table is a real table and not a temp inside the test. I can easily edit that and likely quicker than the GenAI can. It’s copy/pasting some code for me from one spot to another. I also need to add a CREATE OR ALTER to the proc.

    Summary

    A quick use of an AI that easily saved me 5-10 minutes to mock of a scenario and show someone what they were doing wrong and also testing their code. I mock up things regularly to test them, and often do something like this to answer questions. This is a good place where AI can save some time, and might be worth using. I’m also glad to see it recognize and write some decent SQL code for me, especially the insert statement for test data.

  • Checking Myself with GenAI

    I had a suggestion from somone on a place where AI helps them and I decided to try it. The person had an AI summarize their work and if the result wasn’t the intention of the author, then they know know their writing wasn’t clear.

    This post looks at how that worked for me.

    This is part of a series of experiments with AI systems.

    Checking an Editorial

    I wrote an editorial on database Devops that was published recently. I decided to have a few AIs summarize this and see if the result was what I intended. First up, Claude, with a simple prompt: summarize this text (insert here). See the top of the prompt here:

    2025-05_line0025

    The result is shown below and seems to be an accurate summary of the text. This is basically what I was trying to say in the piece. Of course, this isn’t much shorter than the text, but this gives me confidence here in the ability to recognize what I’ve written.

    2025-05_line0027

    In Perplexity, I got this result. This result is similar, but doesn’t mention the author. Instead, this is a summary of the text, not trying to give a voice to the author, which is interesting. Very close to the text above, but this seems slightly drier, taking the text as fact rather than opinion.

    2025-05_line0026

    Perplexity also had some related items at the bottom, which injected a prompt back into the LLM for more info.

    2025-05_line0029

    Last, Copilot. I have a dedicated key on my laptop for this and I pressed it and entered my prompt in the app. This result is shorter and to the point. There are some additional links to click that the bottom.

    2025-05_line0028

    Clicking on one of the items at the bottom injects the text and gets a new result.

    2025-05_line0030

    I tried this with a couple other piece of work, some of which aren’t published. In each case (3 attempts), the summary made sense. I don’t know if that means I am writing anything clearly, but it does help me get a sense of what I’ve written.